Server and method for generating digital content for users of a recommendation system

Abstract

Methods and servers for displaying a digital item to users of a recommendation system are disclosed. The method comprises determining first and second recommendable contents that include the digital item for a first and a second user of a first and a second electronic devices respectively. The digital item is associated with a plurality of actions. The method comprises triggering display of at least some content from the first and second recommendable content including the digital item on the first and second electronic devices respectively. The digital item is associated with a first action triggerable by the first user on the first electronic device and a second action triggerable by the second user on the second electronic device. The first and second actions are selected among the plurality of actions based information about the first and second users respectively.

What is claimed is: 
     
         1 . A method of controlling navigation paths of users of a recommendation system, the recommendation system being hosted by a server, the users being associated with respective electronic devices, the respective electronic devices being communicatively coupled with the server, the method being executable by the server, the method comprising:
 determining, by the server, first recommendable content for a first user of a first electronic device and second recommendable content for a second user of a second electronic device, the first user being distinct from the second user;
 the first and the second recommendable content both including a digital item, the digital item being associated with a plurality of actions; 
   triggering, by the server, display on the first electronic device of at least some content from the first recommendable content including the digital item associated with a first action from the plurality of actions, the first action being triggerable by the first user on the first electronic device,
 the first action being selected from the plurality of actions based on information about the first user; 
   upon the first user triggering the first action, directing the first user on a first navigation path in the recommendation system including the digital item;   triggering, by the server on the second electronic device, display of at least some of the second recommendable content including the digital item associated with a second action from the plurality of actions, the second action being triggerable by the second user on the second electronic device,
 the second action being selected from the plurality of actions based on information about the second user,
 the first action triggerable by the first user being distinct from the second action triggerable by the second user; 
 
   upon the second user triggering the second action, directing the second user on a second navigation path in the recommendation system including the digital item, the first navigation path being different from the second navigation path; wherein
 the digital item is associated with a plurality of third-party providers, the first navigation path being associated with a first one of the plurality of third-party providers; and 
 the second navigation path being associated with a second one of the plurality of third-party providers, the first one of the plurality of third-party providers being different than the second one of the plurality of third-party providers. 
   
     
     
         2 . The method of  claim 1 , wherein the first action being further selected based on the first one from the plurality of third-party providers, and the second action being further selected based on the second one from the plurality of third-party providers. 
     
     
         3 . The method of  claim 2 , wherein the method further comprises:
 determining, by the server, a recommended third-party provider for the first user amongst the plurality of third-party providers associated with the digital item based on endorsement of respective ones from the plurality of third-party providers by other users of the recommendation system, the other users being connected to the first user on the recommendation system,
 the recommended third-party provider being the first one from the plurality of third-party providers associated with the first action. 
   
     
     
         4 . The method of  claim 1 , wherein the first action is provision of a first additional digital item generated by the first one from the plurality of third-party providers, the first additional digital item being subsequent to the digital item in the first navigation path, the second action is provision of a second digital item generated by the second one from the plurality of third-party providers, the second additional digital item being subsequent to the digital item in the second navigation path. 
     
     
         5 . The method of  claim 1 , wherein the determining the first recommendable content and the second recommendable content comprises:
 determining, by the server, a first set of digital items from a pool of potentially recommendable items for the first user based on a relevance of respective content to the first user,
 the first set of digital items being the first recommendable content and including the digital item; 
   determining, by the server, a second set of digital items from the pool of potentially recommendable items for the second user based on a relevance of respective content to the second user,
 the second set of digital items being the second recommendable content and including the digital item. 
   
     
     
         6 . The method of  claim 1 , wherein the method further comprises:
 ranking, by the server employing a Machine Learning Algorithm (MLA), digital items from the first recommendable content into a ranked list of recommendable digital items; and   selecting, by the server, top ranked digital items from the ranked list as the at least some of the first recommendable content to be displayed to the first user, the top ranked digital items including the digital item associated with the first action.   
     
     
         7 . The method of  claim 6 , wherein the method further comprises:
 generating, by the server, a training set for training the MLA, the training set including:
 a first training item dataset comprising information indicative of a training digital item associated with a first training action, 
 a second training item dataset comprising information indicative of the training digital item associated with a second training action, 
 a training user dataset indicative of information about a training user; and 
 a training label indicative of that previously displaying the training item from the first training item dataset to the training user resulted in more user engagement than previously displaying the training item from the second training item dataset; and 
   training, by the server, the MLA based on the training set to predict:
 a first ranking score for the training item from the first training item dataset and a second ranking score for the training item from the second training item dataset, and such that the first ranking score is above the second ranking score. 
   
     
     
         8 . A server for controlling navigation paths of users of a recommendation system, the server hosting the recommendation system, the server being communicatively coupled with a first electronic device associated with a first user and a second electronic device associated with a second user, the first and the second electronic devices being configured to display interfaces of the recommendation system to the first and second users respectively, the server being communicatively coupled with a memory storing potentially recommendable digital items, the server being configured to:
 determine first recommendable content for a first user of a first electronic device and second recommendable content for a second user of a second electronic device, the first user being distinct from the second user;
 the first and the second recommendable content both including a digital item, the digital item being associated with a plurality of actions; 
 
 trigger on the first electronic device, display of at least some content from the first recommendable content including the digital item associated with a first action from the plurality of actions, the first action being triggerable by the first user on the first electronic device,
 the first action being selected from the plurality of actions based on information about the first user; 
 
 upon the first user triggering the first action, direct the first user on a first navigation path in the recommendation system including the digital item; 
 trigger on the second electronic device, display of at least some of the second recommendable content including the digital item associated with a second action from the plurality of actions, the second action being triggerable by the second user on the second electronic device,
 the second action being selected from the plurality of actions based on information about the second user,
 the first action triggerable by the first user being distinct from the second action triggerable by the second user; and 
 
 
 upon the second user triggering the second action, direct the second user on a second navigation path in the recommendation system including the digital item, the first navigation path being different from the second navigation path; wherein
 the digital item is associated with a plurality of third-party providers, the first navigation path being associated with a first one of the plurality of third-party providers; and 
 the second navigation path being associated with a second one of the plurality of third-party providers, the first one of the plurality of third-party providers being different than the second one of the plurality of third-party providers. 
 
 
     
     
         9 . The server of  claim 8 , wherein the first action being further selected based on the first one from the plurality of third-party providers, and the second action being further selected based on the second one from the plurality of third-party providers. 
     
     
         10 . The server of  claim 8 , wherein the first action causes the server to trigger provision of a first additional digital item generated by the first one from the plurality of third-party providers to the first electronic device, the first additional digital item being subsequent to the digital item in the first navigation path, the second action causing the server to trigger provision of a second digital item generated by the second one from the plurality of third-party providers, the second additional digital item being subsequent to the digital item in the second navigation path. 
     
     
         11 . The server of  claim 8 , wherein, upon determining the first recommendable content and the second recommendable content, the server is further configured to:
 determine a first set of digital items from a pool of potentially recommendable items for the first user based on a relevance of respective content to the first user,
 the first set of digital items being the first recommendable content and including the digital item; 
   determine a second set of digital items from the pool of potentially recommendable items for the second user based on a relevance of respective content to the second user,
 the second set of digital items being the second recommendable content and including the digital item. 
   
     
     
         12 . The server of  claim 8 , wherein the server is further configured to:
 rank, by employing a Machine Learning Algorithm (MLA), digital items from the first recommendable content into a ranked list of recommendable items; and   select top ranked digital items from the ranked list as the at least some of the first recommendable content to be displayed to the first user, the top ranked digital items including the digital item associated with the first action.   
     
     
         13 . The server of  claim 12 , wherein the server is further configured to:
 generate a training set for training the MLA, the training set including:
 a first training item dataset comprising information indicative of a training digital item associated with a first training action, 
 a second training item dataset comprising information indicative of the training digital item associated with a second training action, 
 a training user dataset indicative of information about a training user; and 
 a training label indicative of that previously displaying the training item from the first training item dataset to the training user resulted in more user engagement than previously displaying the training item from the second training item dataset; and 
   train the MLA based on the training set to predict:
 a first ranking score for the training item from the first training item dataset and a second ranking score for the training item from the second training item dataset, and such that the first ranking score is above the second ranking score.